Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
On Tue, Sep 19, 2017 at 12:25:15PM -0700, Omar Sandoval wrote: > On Sat, Sep 02, 2017 at 11:17:15PM +0800, Ming Lei wrote: > > Hi, > > > > In Red Hat internal storage test wrt. blk-mq scheduler, we > > found that I/O performance is much bad with mq-deadline, especially > > about sequential I/O on some multi-queue SCSI devcies(lpfc, qla2xxx, > > SRP...) > > > > Turns out one big issue causes the performance regression: requests > > are still dequeued from sw queue/scheduler queue even when ldd's > > queue is busy, so I/O merge becomes quite difficult to make, then > > sequential IO degrades a lot. > > > > The 1st five patches improve this situation, and brings back > > some performance loss. > > Sorry it took so long, I've reviewed or commented on patches 1-6. When > you send v5, could you just send patches 1-6, and split the rest as > their own series? Sure, no problem. Thanks for your review! -- Ming
Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
On Sat, Sep 02, 2017 at 11:17:15PM +0800, Ming Lei wrote: > Hi, > > In Red Hat internal storage test wrt. blk-mq scheduler, we > found that I/O performance is much bad with mq-deadline, especially > about sequential I/O on some multi-queue SCSI devcies(lpfc, qla2xxx, > SRP...) > > Turns out one big issue causes the performance regression: requests > are still dequeued from sw queue/scheduler queue even when ldd's > queue is busy, so I/O merge becomes quite difficult to make, then > sequential IO degrades a lot. > > The 1st five patches improve this situation, and brings back > some performance loss. Sorry it took so long, I've reviewed or commented on patches 1-6. When you send v5, could you just send patches 1-6, and split the rest as their own series?
Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
Likewise with no problems on my work laptop with 4 days uptime. Tested-by: Tom NguyenOn 09/07/2017 04:09 AM, Oleksandr Natalenko wrote: > Feel free to add: > > Tested-by: Oleksandr Natalenko > > since I'm running this on 4 machines without issues. > >> Hi Jens, >> >> Ping...
Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
Feel free to add: Tested-by: Oleksandr Natalenkosince I'm running this on 4 machines without issues. > Hi Jens, > > Ping...
Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
On Tue, Sep 05, 2017 at 09:39:51AM +0800, Ming Lei wrote: > On Mon, Sep 04, 2017 at 11:12:49AM +0200, Paolo Valente wrote: > > > > > Il giorno 02 set 2017, alle ore 17:17, Ming Leiha > > > scritto: > > > > > > Hi, > > > > > > In Red Hat internal storage test wrt. blk-mq scheduler, we > > > found that I/O performance is much bad with mq-deadline, especially > > > about sequential I/O on some multi-queue SCSI devcies(lpfc, qla2xxx, > > > SRP...) > > > > > > Turns out one big issue causes the performance regression: requests > > > are still dequeued from sw queue/scheduler queue even when ldd's > > > queue is busy, so I/O merge becomes quite difficult to make, then > > > sequential IO degrades a lot. > > > > > > The 1st five patches improve this situation, and brings back > > > some performance loss. > > > > > > Patch 6 ~ 7 uses q->queue_depth as hint for setting up > > > scheduler queue depth. > > > > > > Patch 8 ~ 15 improve bio merge via hash table in sw queue, > > > which makes bio merge more efficient than current approch > > > in which only the last 8 requests are checked. Since patch > > > 6~14 converts to the scheduler way of dequeuing one request > > > from sw queue one time for SCSI device, and the times of > > > acquring ctx->lock is increased, and merging bio via hash > > > table decreases holding time of ctx->lock and should eliminate > > > effect from patch 14. > > > > > > With this changes, SCSI-MQ sequential I/O performance is > > > improved much, Paolo reported that mq-deadline performance > > > improved much[2] in his dbench test wrt V2. Also performanc > > > improvement on lpfc/qla2xx was observed with V1.[1] > > > > > > Also Bart worried that this patchset may affect SRP, so provide > > > test data on SCSI SRP this time: > > > > > > - fio(libaio, bs:4k, dio, queue_depth:64, 64 jobs) > > > - system(16 cores, dual sockets, mem: 96G) > > > > > > |v4.13-rc6+* |v4.13-rc6+ | patched v4.13-rc6+ > > > - > > > IOPS(K) | DEADLINE |NONE |NONE > > > - > > > read | 587.81 | 511.96 | 518.51 > > > - > > > randread | 116.44 | 142.99 | 142.46 > > > - > > > write | 580.87 | 536.4 | 582.15 > > > - > > > randwrite | 104.95 | 124.89 | 123.99 > > > - > > > > > > > > > |v4.13-rc6+ |v4.13-rc6+ | patched v4.13-rc6+ > > > - > > > IOPS(K) | DEADLINE |MQ-DEADLINE |MQ-DEADLINE > > > - > > > read | 587.81 | 158.7 | 450.41 > > > - > > > randread | 116.44 | 142.04 | 142.72 > > > - > > > write | 580.87 | 136.61 | 569.37 > > > - > > > randwrite | 104.95 | 123.14 | 124.36 > > > - > > > > > > *: v4.13-rc6+ means v4.13-rc6 with block for-next > > > > > > > > > Please consider to merge to V4.4. > > > > > > [1] http://marc.info/?l=linux-block=150151989915776=2 > > > [2] https://marc.info/?l=linux-block=150217980602843=2 > > > > > > V4: > > > - add Reviewed-by tag > > > - some trival change: typo fix in commit log or comment, > > > variable name, no actual functional change > > > > > > V3: > > > - totally round robin for picking req from ctx, as suggested > > > by Bart > > > - remove one local variable in __sbitmap_for_each_set() > > > - drop patches of single dispatch list, which can improve > > > performance on mq-deadline, but cause a bit degrade on > > > none because all hctxs need to be checked after ->dispatch > > > is flushed. Will post it again once it is mature. > > > - rebase on v4.13-rc6 with block for-next > > > > > > V2: > > > - dequeue request from sw queues in round roubin's style > > > as suggested by Bart, and introduces one helper in sbitmap > > > for this purpose > > > - improve bio merge via hash table from sw queue > > > - add comments about using DISPATCH_BUSY state in lockless way, > > > simplifying handling on busy state, > > > - hold ctx->lock when clearing ctx busy bit as suggested > > > by Bart > > > > > > > > > > Tested-by: Paolo Valente > > Hi Jens, > > Is there any chance to make this patchset merged to V4.4? Hi Jens, Ping... Thanks, Ming
Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
On Mon, Sep 04, 2017 at 11:12:49AM +0200, Paolo Valente wrote: > > > Il giorno 02 set 2017, alle ore 17:17, Ming Leiha > > scritto: > > > > Hi, > > > > In Red Hat internal storage test wrt. blk-mq scheduler, we > > found that I/O performance is much bad with mq-deadline, especially > > about sequential I/O on some multi-queue SCSI devcies(lpfc, qla2xxx, > > SRP...) > > > > Turns out one big issue causes the performance regression: requests > > are still dequeued from sw queue/scheduler queue even when ldd's > > queue is busy, so I/O merge becomes quite difficult to make, then > > sequential IO degrades a lot. > > > > The 1st five patches improve this situation, and brings back > > some performance loss. > > > > Patch 6 ~ 7 uses q->queue_depth as hint for setting up > > scheduler queue depth. > > > > Patch 8 ~ 15 improve bio merge via hash table in sw queue, > > which makes bio merge more efficient than current approch > > in which only the last 8 requests are checked. Since patch > > 6~14 converts to the scheduler way of dequeuing one request > > from sw queue one time for SCSI device, and the times of > > acquring ctx->lock is increased, and merging bio via hash > > table decreases holding time of ctx->lock and should eliminate > > effect from patch 14. > > > > With this changes, SCSI-MQ sequential I/O performance is > > improved much, Paolo reported that mq-deadline performance > > improved much[2] in his dbench test wrt V2. Also performanc > > improvement on lpfc/qla2xx was observed with V1.[1] > > > > Also Bart worried that this patchset may affect SRP, so provide > > test data on SCSI SRP this time: > > > > - fio(libaio, bs:4k, dio, queue_depth:64, 64 jobs) > > - system(16 cores, dual sockets, mem: 96G) > > > > |v4.13-rc6+* |v4.13-rc6+ | patched v4.13-rc6+ > > - > > IOPS(K) | DEADLINE |NONE |NONE > > - > > read | 587.81 | 511.96 | 518.51 > > - > > randread | 116.44 | 142.99 | 142.46 > > - > > write | 580.87 | 536.4 | 582.15 > > - > > randwrite | 104.95 | 124.89 | 123.99 > > - > > > > > > |v4.13-rc6+ |v4.13-rc6+ | patched v4.13-rc6+ > > - > > IOPS(K) | DEADLINE |MQ-DEADLINE |MQ-DEADLINE > > - > > read | 587.81 | 158.7 | 450.41 > > - > > randread | 116.44 | 142.04 | 142.72 > > - > > write | 580.87 | 136.61 | 569.37 > > - > > randwrite | 104.95 | 123.14 | 124.36 > > - > > > > *: v4.13-rc6+ means v4.13-rc6 with block for-next > > > > > > Please consider to merge to V4.4. > > > > [1] http://marc.info/?l=linux-block=150151989915776=2 > > [2] https://marc.info/?l=linux-block=150217980602843=2 > > > > V4: > > - add Reviewed-by tag > > - some trival change: typo fix in commit log or comment, > > variable name, no actual functional change > > > > V3: > > - totally round robin for picking req from ctx, as suggested > > by Bart > > - remove one local variable in __sbitmap_for_each_set() > > - drop patches of single dispatch list, which can improve > > performance on mq-deadline, but cause a bit degrade on > > none because all hctxs need to be checked after ->dispatch > > is flushed. Will post it again once it is mature. > > - rebase on v4.13-rc6 with block for-next > > > > V2: > > - dequeue request from sw queues in round roubin's style > > as suggested by Bart, and introduces one helper in sbitmap > > for this purpose > > - improve bio merge via hash table from sw queue > > - add comments about using DISPATCH_BUSY state in lockless way, > > simplifying handling on busy state, > > - hold ctx->lock when clearing ctx busy bit as suggested > > by Bart > > > > > > Tested-by: Paolo Valente Hi Jens, Is there any chance to make this patchset merged to V4.4? Thanks, Ming
Re: [PATCH V4 00/14] blk-mq-sched: improve SCSI-MQ performance
> Il giorno 02 set 2017, alle ore 17:17, Ming Leiha > scritto: > > Hi, > > In Red Hat internal storage test wrt. blk-mq scheduler, we > found that I/O performance is much bad with mq-deadline, especially > about sequential I/O on some multi-queue SCSI devcies(lpfc, qla2xxx, > SRP...) > > Turns out one big issue causes the performance regression: requests > are still dequeued from sw queue/scheduler queue even when ldd's > queue is busy, so I/O merge becomes quite difficult to make, then > sequential IO degrades a lot. > > The 1st five patches improve this situation, and brings back > some performance loss. > > Patch 6 ~ 7 uses q->queue_depth as hint for setting up > scheduler queue depth. > > Patch 8 ~ 15 improve bio merge via hash table in sw queue, > which makes bio merge more efficient than current approch > in which only the last 8 requests are checked. Since patch > 6~14 converts to the scheduler way of dequeuing one request > from sw queue one time for SCSI device, and the times of > acquring ctx->lock is increased, and merging bio via hash > table decreases holding time of ctx->lock and should eliminate > effect from patch 14. > > With this changes, SCSI-MQ sequential I/O performance is > improved much, Paolo reported that mq-deadline performance > improved much[2] in his dbench test wrt V2. Also performanc > improvement on lpfc/qla2xx was observed with V1.[1] > > Also Bart worried that this patchset may affect SRP, so provide > test data on SCSI SRP this time: > > - fio(libaio, bs:4k, dio, queue_depth:64, 64 jobs) > - system(16 cores, dual sockets, mem: 96G) > > |v4.13-rc6+* |v4.13-rc6+ | patched v4.13-rc6+ > - > IOPS(K) | DEADLINE |NONE |NONE > - > read | 587.81 | 511.96 | 518.51 > - > randread | 116.44 | 142.99 | 142.46 > - > write | 580.87 | 536.4 | 582.15 > - > randwrite | 104.95 | 124.89 | 123.99 > - > > > |v4.13-rc6+ |v4.13-rc6+ | patched v4.13-rc6+ > - > IOPS(K) | DEADLINE |MQ-DEADLINE |MQ-DEADLINE > - > read | 587.81 | 158.7 | 450.41 > - > randread | 116.44 | 142.04 | 142.72 > - > write | 580.87 | 136.61 | 569.37 > - > randwrite | 104.95 | 123.14 | 124.36 > - > > *: v4.13-rc6+ means v4.13-rc6 with block for-next > > > Please consider to merge to V4.4. > > [1] http://marc.info/?l=linux-block=150151989915776=2 > [2] https://marc.info/?l=linux-block=150217980602843=2 > > V4: > - add Reviewed-by tag > - some trival change: typo fix in commit log or comment, > variable name, no actual functional change > > V3: > - totally round robin for picking req from ctx, as suggested > by Bart > - remove one local variable in __sbitmap_for_each_set() > - drop patches of single dispatch list, which can improve > performance on mq-deadline, but cause a bit degrade on > none because all hctxs need to be checked after ->dispatch > is flushed. Will post it again once it is mature. > - rebase on v4.13-rc6 with block for-next > > V2: > - dequeue request from sw queues in round roubin's style > as suggested by Bart, and introduces one helper in sbitmap > for this purpose > - improve bio merge via hash table from sw queue > - add comments about using DISPATCH_BUSY state in lockless way, > simplifying handling on busy state, > - hold ctx->lock when clearing ctx busy bit as suggested > by Bart > > Tested-by: Paolo Valente > Ming Lei (14): > blk-mq-sched: fix scheduler bad performance > sbitmap: introduce __sbitmap_for_each_set() > blk-mq: introduce blk_mq_dispatch_rq_from_ctx() > blk-mq-sched: move actual dispatching into one helper > blk-mq-sched: improve dispatching from sw queue > blk-mq-sched: don't dequeue request until all in ->dispatch are >flushed > blk-mq-sched: introduce blk_mq_sched_queue_depth() > blk-mq-sched: use q->queue_depth as hint for q->nr_requests > block: introduce rqhash helpers > block: move actual bio merge code into __elv_merge > block: add check on elevator for supporting bio merge via hashtable >from blk-mq sw queue > block: introduce .last_merge and .hash to blk_mq_ctx